© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1501
    Prev
    Next
    INDEX
    Explanations

    states

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pyongyang
    -0.27
     ninete
    -0.26
     Spokane
    -0.26
    èķĪ
    -0.25
     Appalachian
    -0.24
     Barang
    -0.24
     Baltic
    -0.23
    ä¹ı
    -0.23
     Indones
    -0.23
     Malays
    -0.23
    POSITIVE LOGITS
     New
    0.27
    %X
    0.26
    :maj
    0.26
    ]int
    0.26
     North
    0.26
     à¹Ģมษายà¸Ļ
    0.25
     South
    0.25
    _codigo
    0.25
    /↵↵↵↵
    0.25
     state
    0.24
    Activations Density 6.025%

    No Known Activations